An Improved Data-driven Soft Sensor Modeling Algorithm Based on Twin Support Vector Regression for Sugar Cane Crystallization
- 10.2991/lemcs-15.2015.138How to use a DOI?
- Soft sensor; Data-driven modeling; Twin support vector regression; Punishment weight; Structural risk
Due to the problem that some key parameters, such as mother liquor supersaturation, mother liquor purity, crystal content and crystal size distribution, cannot be measured on-line during sugar cane crystallization, an improved data-driven soft sensor modeling algorithm based on twin support vector regression is proposed, following improvements are taken based on traditional data-driven model. The complexity of data-driven model decreases by adding a regularization term, which can transform empirical risk into structural risk. Computational speed increases and computational time decreases efficiently by modifying the size of kernel function matrix. Different punishment weight is given to sample sets according to their own importance, which can increase the algorithm’s generalization ability and avoid over-fitting problems to a certain degree. Experimental results show that comparing with traditional data-driven soft sensor modeling,this improved algorithm has better prediction result and less prediction error than traditional data-driven modeling method.
- © 2015, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Yanmei Meng AU - Kangyuan Zheng AU - Xiaoyuan Ma AU - Wenxing Li PY - 2015/07 DA - 2015/07 TI - An Improved Data-driven Soft Sensor Modeling Algorithm Based on Twin Support Vector Regression for Sugar Cane Crystallization BT - Proceedings of the International Conference on Logistics, Engineering, Management and Computer Science PB - Atlantis Press SP - 704 EP - 708 SN - 1951-6851 UR - https://doi.org/10.2991/lemcs-15.2015.138 DO - 10.2991/lemcs-15.2015.138 ID - Meng2015/07 ER -